【"The approach that we took is first we basically built custom silicon that could handle inference for our ranking and recommendation type stuff, so Reels, News Feed, ads," he said.
"That was consuming a lot of GPUs. When we were able to move that to our own silicon, we're now able to use the more expensive Nvidia GPUs only for training. At some point we will hopefully have silicon ourselves that we can be using at first for training some of the simpler things, then eventually training these really large models."】很清楚啊，推理was consuming。然后还有at some point呢，作为$Meta(META)$ 股东，当然希望小扎能给公司省钱咯。

NVDIA的卡用来推理可能太贵了

这个周末的主题就是各路人马都出来马后炮：ai也在降本增效，未来性能提升的同时降低对卡的需求

推理要求不高，可以用别家的方案，更便宜的更高效的卡